Smart Diagnosis of Active Systems

Automated diagnosis has always been a challenging task to AI. When model-based diagnosis is adopted, a model of the system is required in order to generate a set of diagnoses based on a collection of observations, where a diagnosis is a set of faulty components or, more generally, a set of faults ascribed to components. An active system (AS) is an asynchronous, distributed discrete-event system, whose model consists of a topology (how components are connected to one another), and a communicating automaton for each component (the mode in which a component reacts to events). A problem afflicting all model-based approaches to diagnosis is a possibly large number of diagnoses explaining the observations, which may jeopardize the task of a diagnostician in charge of monitoring the system, owing to the cognitive overload raised by an overwhelming number of faulty scenarios to examine. This is exacerbated in critical application domains, where, under uncertain conditions, an artificial agent is supposed to perform recovery actions in real-time, even in the order of milliseconds, to possibly restore the system. To make diagnosis of ASs viable in critical, real-time application domains, a Smart Diagnosis Engine is presented, which is grounded on two heuristics: (1) if a diagnosis δ is a superset of a diagnosis δ', then δ is ignored (minimality); (2) if the cardinality (number of faults) of a diagnosis δ is lower than the cardinality of a diagnosis δ', then δ is generated before δ' (sorting). Consequently, the diagnosis output consists in a sequence of minimal diagnoses that are generated in ascending order by cardinality. As indicated by the experimental results, the overall improvement is twofold: most likely diagnoses are generated upfront, thereby supporting real-time recovery actions; also, the abductive search in the behavior space of the AS is reduced considerably, owing to the pruning of the trajectories that will not generate minimal diagnoses, thereby resulting in an impressive reduction in both memory allocation and processing time.